https://intelligentartifact.com/jev/ Recent content in Jev on Intelligent Artifact Hugo en-us Mon, 21 Sep 2026 11:53:59 -0400 https://intelligentartifact.com/jev/examples/ Mon, 21 Sep 2026 11:53:59 -0400 https://intelligentartifact.com/jev/examples/ A browsable starting list of Jev projects: routing, guardrails, scoring, agents, data tools, and games. Leads to investigate, not tested endorsements. https://intelligentartifact.com/jev/call-coach-ai/ Mon, 21 Sep 2026 11:53:59 -0400 https://intelligentartifact.com/jev/call-coach-ai/ A concrete Jev integration: batched typed judgments, a deterministic playbook, and a human making the final call. https://intelligentartifact.com/jev/jev-semif-local-cloud-model-router-sam-witteveen/ Mon, 21 Sep 2026 07:30:38 -0700 https://intelligentartifact.com/jev/jev-semif-local-cloud-model-router-sam-witteveen/ Sam Witteveen builds a local model router that combines task classification, difficulty, privacy, and web-access decisions, then swaps cloud Jev for local Semif to keep the routing check on-device. https://intelligentartifact.com/jev/jev-shaped-problems-nate-b-jones/ Mon, 21 Sep 2026 07:00:39 -0700 https://intelligentartifact.com/jev/jev-shaped-problems-nate-b-jones/ Nate B Jones defines Jev-shaped problems—complicated input, constrained decisions—and maps four ways a cheap general-purpose classifier can fit into everyday software. https://intelligentartifact.com/jev/jev-game-testing-pr-triage-model-routing-cole-medin/ Mon, 21 Sep 2026 06:45:16 -0700 https://intelligentartifact.com/jev/jev-game-testing-pr-triage-model-routing-cole-medin/ Cole Medin tests Jev as a game controller, pull-request triage step, and model router, arguing that fast, general-purpose classification complements rather than replaces generative AI. https://intelligentartifact.com/jev/open-jev-models-local-classification-sam-witteveen/ Sun, 20 Sep 2026 08:00:15 -0700 https://intelligentartifact.com/jev/open-jev-models-local-classification-sam-witteveen/ Sam Witteveen tests seven open Jev-style projects, comparing their classification techniques, local demos, and limits—and why harder decisions still need a reasoning model. https://intelligentartifact.com/jev/jev-claude-code-cheap-feedback-loops-ray-amjad/ Fri, 18 Sep 2026 08:02:30 -0700 https://intelligentartifact.com/jev/jev-claude-code-cheap-feedback-loops-ray-amjad/ Ray Amjad explores Jev as a fast screening layer for coding agents: skill selection, browser verification, comment audits, qualitative linters, and code-review triage. https://intelligentartifact.com/jev/jev-classification-typed-decisions-sam-witteveen/ Fri, 18 Sep 2026 08:00:13 -0700 https://intelligentartifact.com/jev/jev-classification-typed-decisions-sam-witteveen/ Sam Witteveen tests Jev's choice, score, and yes/no decisions, explores practical classification workflows, and separates schema reliability from correctness and undisclosed architecture. https://intelligentartifact.com/jev/jev-whats-next-after-rlhf/ Fri, 31 Jul 2026 16:30:06 -0700 https://intelligentartifact.com/jev/jev-whats-next-after-rlhf/ Diogo Almeida argues that pleasing a human and running reliable software are different objectives. His case for moving beyond AI assistance—and why he says Jev's approach is not simply RLVR.